{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/attention-dropout/papers/106","list_of":"/method/attention-dropout","method":"Attention Dropout","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":106,"pages_in_order":109,"rows_per_page":100,"rows":[10501,10600],"of":10892,"counts":{"archive_papers_tagged":10892,"with_a_code_link":4634,"where_syntology_ran_a_sample":1270,"not_listed_spam_title":0,"listed":10892,"listed_where_code_ran":1270,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1043,"every_run_a_failure_of_syntologys_instrument":227,"listed_with_a_run_with_no_instrument_failure":1043,"listed_every_run_a_failure_of_syntologys_instrument":227,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/attention-dropout","prev":"/method/attention-dropout/papers/105","next":"/method/attention-dropout/papers/107","papers":[{"paper":"/paper/parallel-iterative-edit-models-for-local","slug":"parallel-iterative-edit-models-for-local","title":"Parallel Iterative Edit Models for Local Sequence Transduction","date":"2019-10-07","arxiv_id":"1910.02893","n_code_links":1,"syntology":null},{"paper":"/paper/named-entity-recognition-is-there-a-glass","slug":"named-entity-recognition-is-there-a-glass","title":"Named Entity Recognition -- Is there a glass ceiling?","date":"2019-10-06","arxiv_id":"1910.02403","n_code_links":1,"syntology":null},{"paper":null,"slug":"distilling-transformers-into-simple-neural","title":"Distilling BERT into Simple Neural Networks with Unlabeled Transfer Data","date":"2019-10-04","arxiv_id":"1910.01769","n_code_links":0,"syntology":null},{"paper":"/paper/fine-grained-sentiment-classification-using","slug":"fine-grained-sentiment-classification-using","title":"Fine-grained Sentiment Classification using BERT","date":"2019-10-04","arxiv_id":"1910.03474","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/zero-memory-optimization-towards-training-a","slug":"zero-memory-optimization-towards-training-a","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","date":"2019-10-04","arxiv_id":"1910.02054","n_code_links":10,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["NVIDIA/Megatron-LM","microsoft/DeepSpeed"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/towards-understanding-of-medical-randomized","slug":"towards-understanding-of-medical-randomized","title":"Towards Understanding of Medical Randomized Controlled Trials by Conclusion Generation","date":"2019-10-03","arxiv_id":"1910.01462","n_code_links":1,"syntology":null},{"paper":null,"slug":"cracking-the-contextual-commonsense-code","title":"Cracking the Contextual Commonsense Code: Understanding Commonsense Reasoning Aptitude of Deep Contextual Representations","date":"2019-10-02","arxiv_id":"1910.01157","n_code_links":0,"syntology":null},{"paper":"/paper/distilbert-a-distilled-version-of-bert","slug":"distilbert-a-distilled-version-of-bert","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","date":"2019-10-02","arxiv_id":"1910.01108","n_code_links":37,"syntology":{"ran":21,"of":27,"n_ran_checked":13,"n_instrument":8,"unverified":6,"pointer_only":2,"phrase":"21 ran (of which 5 constructed an object rather than computing a result; 13 with no instrument failure: 3 honoured, 1 violated, 9 with no contract checked; 8 where Syntology's instrument failed) · 6 unverified","official":{"repos":["huggingface/swift-coreml-transformers","huggingface/transformers"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/exploiting-bert-for-end-to-end-aspect-based","slug":"exploiting-bert-for-end-to-end-aspect-based","title":"Exploiting BERT for End-to-End Aspect-based Sentiment Analysis","date":"2019-10-02","arxiv_id":"1910.00883","n_code_links":1,"syntology":null},{"paper":"/paper/linking-artificial-and-human-neural","slug":"linking-artificial-and-human-neural","title":"Linking artificial and human neural representations of language","date":"2019-10-02","arxiv_id":"1910.01244","n_code_links":1,"syntology":{"ran":8,"of":11,"n_ran_checked":4,"n_instrument":4,"unverified":3,"pointer_only":3,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":null,"slug":"bert-for-question-generation","title":"BERT for Question Generation","date":"2019-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/specializing-word-embeddings-for-parsing-by","slug":"specializing-word-embeddings-for-parsing-by","title":"Specializing Word Embeddings (for Parsing) by Information Bottleneck","date":"2019-10-01","arxiv_id":"1910.00163","n_code_links":1,"syntology":null},{"paper":null,"slug":"tmlab-generative-enhanced-model-gem-for","title":"TMLab: Generative Enhanced Model (GEM) for adversarial attacks","date":"2019-10-01","arxiv_id":"1910.00337","n_code_links":0,"syntology":null},{"paper":null,"slug":"vae-pgn-based-abstractive-model-in-multi","title":"VAE-PGN based Abstractive Model in Multi-stage Architecture for Text Summarization","date":"2019-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"end-to-end-resume-parsing-and-finding","title":"End-to-End Resume Parsing and Finding Candidates for a Job Description using BERT","date":"2019-09-30","arxiv_id":"1910.03089","n_code_links":0,"syntology":null},{"paper":"/paper/fake-news-detection-using-deep-learning","slug":"fake-news-detection-using-deep-learning","title":"Fake news detection using Deep Learning","date":"2019-09-29","arxiv_id":"1910.03496","n_code_links":2,"syntology":null},{"paper":"/paper/hatemonitors-language-agnostic-abuse","slug":"hatemonitors-language-agnostic-abuse","title":"HateMonitors: Language Agnostic Abuse Detection in Social Media","date":"2019-09-27","arxiv_id":"1909.12642","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-use-of-bert-for-neural-machine","title":"On the use of BERT for Neural Machine Translation","date":"2019-09-27","arxiv_id":"1909.12744","n_code_links":0,"syntology":null},{"paper":null,"slug":"reweighted-proximal-pruning-for-large-scale-1","title":"Reweighted Proximal Pruning for Large-Scale Language Representation","date":"2019-09-27","arxiv_id":"1909.12486","n_code_links":0,"syntology":null},{"paper":"/paper/albert-a-lite-bert-for-self-supervised","slug":"albert-a-lite-bert-for-self-supervised","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","date":"2019-09-26","arxiv_id":"1909.11942","n_code_links":48,"syntology":{"ran":81,"of":126,"n_ran_checked":59,"n_instrument":22,"unverified":45,"pointer_only":28,"phrase":"81 ran (of which 17 constructed an object rather than computing a result; 59 with no instrument failure: 4 honoured, 0 violated, 55 with no contract checked; 22 where Syntology's instrument failed) · 45 unverified","official":{"repos":["google-research/ALBERT"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"aspect-and-opinion-term-extraction-for-aspect","title":"Aspect and Opinion Term Extraction for Hotel Reviews using Transfer Learning and Auxiliary Labels","date":"2019-09-26","arxiv_id":"1909.11879","n_code_links":0,"syntology":null},{"paper":null,"slug":"biomedical-relation-extraction-with-pre","title":"Biomedical relation extraction with pre-trained language representations and minimal task-specific architecture","date":"2019-09-26","arxiv_id":"1909.12411","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-pre-trained-multilingual-models","title":"Improving Pre-Trained Multilingual Models with Vocabulary Expansion","date":"2019-09-26","arxiv_id":"1909.12440","n_code_links":0,"syntology":null},{"paper":null,"slug":"extreme-language-model-compression-with-1","title":"Extremely Small BERT Models from Mixed-Vocabulary Training","date":"2019-09-25","arxiv_id":"1909.11687","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-detect-opinion-snippet-for-aspect","title":"Learning to Detect Opinion Snippet for Aspect-Based Sentiment Analysis","date":"2019-09-25","arxiv_id":"1909.11297","n_code_links":0,"syntology":null},{"paper":"/paper/mixout-effective-regularization-to-finetune","slug":"mixout-effective-regularization-to-finetune","title":"Mixout: Effective Regularization to Finetune Large-scale Pretrained Language Models","date":"2019-09-25","arxiv_id":"1909.11299","n_code_links":2,"syntology":null},{"paper":null,"slug":"technical-report-on-conversational-question","title":"Technical report on Conversational Question Answering","date":"2019-09-24","arxiv_id":"1909.10772","n_code_links":0,"syntology":null},{"paper":null,"slug":"understanding-semantics-from-speech-through","title":"Understanding Semantics from Speech Through Pre-training","date":"2019-09-24","arxiv_id":"1909.10924","n_code_links":0,"syntology":null},{"paper":"/paper/190910351","slug":"190910351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","date":"2019-09-23","arxiv_id":"1909.10351","n_code_links":10,"syntology":{"ran":0,"of":4,"n_ran_checked":0,"n_instrument":0,"unverified":4,"pointer_only":4,"phrase":"0 ran · 4 unverified","official":{"repos":["huawei-noah/Pretrained-Language-Model"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"paper":"/paper/190910430","slug":"190910430","title":"Does BERT Make Any Sense? Interpretable Word Sense Disambiguation with Contextualized Embeddings","date":"2019-09-23","arxiv_id":"1909.10430","n_code_links":1,"syntology":null},{"paper":"/paper/automatic-identification-and-normalisation-of","slug":"automatic-identification-and-normalisation-of","title":"Automatic Identification and Normalisation of Physical Measurements in Scientific Literature","date":"2019-09-23","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/portuguese-named-entity-recognition-using-1","slug":"portuguese-named-entity-recognition-using-1","title":"Portuguese Named Entity Recognition using BERT-CRF","date":"2019-09-23","arxiv_id":"1909.10649","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["neuralmind-ai/portuguese-bert"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"bert-meets-chinese-word-segmentation","title":"BERT Meets Chinese Word Segmentation","date":"2019-09-20","arxiv_id":"1909.09292","n_code_links":0,"syntology":null},{"paper":"/paper/allennlp-interpret-a-framework-for-explaining","slug":"allennlp-interpret-a-framework-for-explaining","title":"AllenNLP Interpret: A Framework for Explaining Predictions of NLP Models","date":"2019-09-19","arxiv_id":"1909.09251","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-ways-to-incorporate-additional","title":"How Additional Knowledge can Improve Natural Language Commonsense Question Answering?","date":"2019-09-19","arxiv_id":"1909.08855","n_code_links":0,"syntology":null},{"paper":"/paper/summary-level-training-of-sentence-rewriting","slug":"summary-level-training-of-sentence-rewriting","title":"Summary Level Training of Sentence Rewriting for Abstractive Summarization","date":"2019-09-19","arxiv_id":"1909.08752","n_code_links":0,"syntology":null},{"paper":"/paper/enriching-bert-with-knowledge-graph","slug":"enriching-bert-with-knowledge-graph","title":"Enriching BERT with Knowledge Graph Embeddings for Document Classification","date":"2019-09-18","arxiv_id":"1909.08402","n_code_links":1,"syntology":null},{"paper":"/paper/improving-natural-language-inference-with-a","slug":"improving-natural-language-inference-with-a","title":"Improving Natural Language Inference with a Pretrained Parser","date":"2019-09-18","arxiv_id":"1909.08217","n_code_links":1,"syntology":null},{"paper":"/paper/language-models-and-automated-essay-scoring","slug":"language-models-and-automated-essay-scoring","title":"Language models and Automated Essay Scoring","date":"2019-09-18","arxiv_id":"1909.09482","n_code_links":1,"syntology":null},{"paper":null,"slug":"using-bert-for-word-sense-disambiguation","title":"Using BERT for Word Sense Disambiguation","date":"2019-09-18","arxiv_id":"1909.08358","n_code_links":0,"syntology":null},{"paper":"/paper/do-nlp-models-know-numbers-probing-numeracy","slug":"do-nlp-models-know-numbers-probing-numeracy","title":"Do NLP Models Know Numbers? Probing Numeracy in Embeddings","date":"2019-09-17","arxiv_id":"1909.07940","n_code_links":1,"syntology":null},{"paper":"/paper/extracting-evidence-of-supplement-drug","slug":"extracting-evidence-of-supplement-drug","title":"SUPP.AI: Finding Evidence for Supplement-Drug Interactions","date":"2019-09-17","arxiv_id":"1909.08135","n_code_links":1,"syntology":null},{"paper":"/paper/k-bert-enabling-language-representation-with","slug":"k-bert-enabling-language-representation-with","title":"K-BERT: Enabling Language Representation with Knowledge Graph","date":"2019-09-17","arxiv_id":"1909.07606","n_code_links":2,"syntology":null},{"paper":"/paper/megatron-lm-training-multi-billion-parameter","slug":"megatron-lm-training-multi-billion-parameter","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","date":"2019-09-17","arxiv_id":"1909.08053","n_code_links":10,"syntology":{"ran":12,"of":47,"n_ran_checked":7,"n_instrument":5,"unverified":35,"pointer_only":15,"phrase":"12 ran (of which 2 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 35 unverified","official":{"repos":["NVIDIA/Megatron-LM"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"simple-yet-effective-bridge-reasoning-for","title":"Simple yet Effective Bridge Reasoning for Open-Domain Multi-Hop Question Answering","date":"2019-09-17","arxiv_id":"1909.07597","n_code_links":0,"syntology":null},{"paper":"/paper/span-based-joint-entity-and-relation","slug":"span-based-joint-entity-and-relation","title":"Span-based Joint Entity and Relation Extraction with Transformer Pre-training","date":"2019-09-17","arxiv_id":"1909.07755","n_code_links":3,"syntology":null},{"paper":"/paper/probing-natural-language-inference-models","slug":"probing-natural-language-inference-models","title":"Probing Natural Language Inference Models through Semantic Fragments","date":"2019-09-16","arxiv_id":"1909.07521","n_code_links":3,"syntology":null},{"paper":"/paper/cross-lingual-bert-transformation-for-zero","slug":"cross-lingual-bert-transformation-for-zero","title":"Cross-Lingual BERT Transformation for Zero-Shot Dependency Parsing","date":"2019-09-15","arxiv_id":"1909.06775","n_code_links":1,"syntology":null},{"paper":"/paper/tree-transformer-integrating-tree-structures","slug":"tree-transformer-integrating-tree-structures","title":"Tree Transformer: Integrating Tree Structures into Self-Attention","date":"2019-09-14","arxiv_id":"1909.06639","n_code_links":3,"syntology":{"ran":9,"of":10,"n_ran_checked":7,"n_instrument":2,"unverified":1,"pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["yaushian/Tree-Transformer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/addressing-semantic-drift-in-question","slug":"addressing-semantic-drift-in-question","title":"Addressing Semantic Drift in Question Generation for Semi-Supervised Question Answering","date":"2019-09-13","arxiv_id":"1909.06356","n_code_links":2,"syntology":{"ran":13,"of":19,"n_ran_checked":11,"n_instrument":2,"unverified":6,"pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 1 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","official":{"repos":["ZhangShiyue/QGforQA"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/towards-open-domain-named-entity-recognition","slug":"towards-open-domain-named-entity-recognition","title":"Neural Correction Model for Open-Domain Named Entity Recognition","date":"2019-09-13","arxiv_id":"1909.06058","n_code_links":1,"syntology":null},{"paper":null,"slug":"measuring-domain-portability-and","title":"Measuring Domain Portability and ErrorPropagation in Biomedical QA","date":"2019-09-12","arxiv_id":"1909.09704","n_code_links":0,"syntology":null},{"paper":"/paper/q-bert-hessian-based-ultra-low-precision","slug":"q-bert-hessian-based-ultra-low-precision","title":"Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT","date":"2019-09-12","arxiv_id":"1909.05840","n_code_links":0,"syntology":null},{"paper":"/paper/uer-an-open-source-toolkit-for-pre-training","slug":"uer-an-open-source-toolkit-for-pre-training","title":"UER: An Open-Source Toolkit for Pre-training Models","date":"2019-09-12","arxiv_id":"1909.05658","n_code_links":2,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["dbiir/UER-py"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/bertgrid-contextualized-embedding-for-2d","slug":"bertgrid-contextualized-embedding-for-2d","title":"BERTgrid: Contextualized Embedding for 2D Document Representation and Understanding","date":"2019-09-11","arxiv_id":"1909.04948","n_code_links":2,"syntology":null},{"paper":"/paper/from-english-to-code-switching-transfer","slug":"from-english-to-code-switching-transfer","title":"From English to Code-Switching: Transfer Learning with Strong Morphological Clues","date":"2019-09-11","arxiv_id":"1909.05158","n_code_links":1,"syntology":null},{"paper":"/paper/frustratingly-easy-natural-question-answering","slug":"frustratingly-easy-natural-question-answering","title":"Frustratingly Easy Natural Question Answering","date":"2019-09-11","arxiv_id":"1909.05286","n_code_links":0,"syntology":null},{"paper":"/paper/how-does-bert-answer-questions-a-layer-wise","slug":"how-does-bert-answer-questions-a-layer-wise","title":"How Does BERT Answer Questions? A Layer-Wise Analysis of Transformer Representations","date":"2019-09-11","arxiv_id":"1909.04925","n_code_links":2,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["bvanaken/explain-BERT-QA"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"bert-based-arabic-social-media","title":"BERT-Based Arabic Social Media Author Profiling","date":"2019-09-09","arxiv_id":"1909.04181","n_code_links":0,"syntology":null},{"paper":"/paper/knowledge-enhanced-contextual-word","slug":"knowledge-enhanced-contextual-word","title":"Knowledge Enhanced Contextual Word Representations","date":"2019-09-09","arxiv_id":"1909.04164","n_code_links":1,"syntology":null},{"paper":"/paper/pretrained-language-models-for-sequential","slug":"pretrained-language-models-for-sequential","title":"Pretrained Language Models for Sequential Sentence Classification","date":"2019-09-09","arxiv_id":"1909.04054","n_code_links":1,"syntology":null},{"paper":"/paper/reasoning-over-semantic-level-graph-for-fact","slug":"reasoning-over-semantic-level-graph-for-fact","title":"Reasoning Over Semantic-Level Graph for Fact Checking","date":"2019-09-09","arxiv_id":"1909.03745","n_code_links":0,"syntology":null},{"paper":"/paper/span-selection-pre-training-for-question","slug":"span-selection-pre-training-for-question","title":"Span Selection Pre-training for Question Answering","date":"2019-09-09","arxiv_id":"1909.04120","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["IBM/span-selection-pretraining"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"commonsense-knowledge-bert-for-level-2","title":"Commonsense Knowledge + BERT for Level 2 Reading Comprehension Ability Test","date":"2019-09-08","arxiv_id":"1909.03415","n_code_links":0,"syntology":null},{"paper":null,"slug":"czech-text-processing-with-contextual","title":"Czech Text Processing with Contextual Embeddings: POS Tagging, Lemmatization, Parsing and NER","date":"2019-09-08","arxiv_id":"1909.03544","n_code_links":0,"syntology":null},{"paper":"/paper/entity-relation-and-event-extraction-with","slug":"entity-relation-and-event-extraction-with","title":"Entity, Relation, and Event Extraction with Contextualized Span Representations","date":"2019-09-08","arxiv_id":"1909.03546","n_code_links":4,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["dwadden/dygiepp"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"multi-task-bidirectional-transformer","title":"Multi-Task Bidirectional Transformer Representations for Irony Detection","date":"2019-09-08","arxiv_id":"1909.03526","n_code_links":0,"syntology":null},{"paper":"/paper/symmetric-regularization-based-bert-for-pair","slug":"symmetric-regularization-based-bert-for-pair","title":"Symmetric Regularization based BERT for Pair-wise Semantic Reasoning","date":"2019-09-08","arxiv_id":"1909.03405","n_code_links":1,"syntology":null},{"paper":"/paper/transfer-learning-robustness-in-multi-class","slug":"transfer-learning-robustness-in-multi-class","title":"Transfer Learning Robustness in Multi-Class Categorization by Fine-Tuning Pre-Trained Contextualized Language Models","date":"2019-09-08","arxiv_id":"1909.03564","n_code_links":1,"syntology":null},{"paper":"/paper/a-novel-hierarchical-binary-tagging-framework","slug":"a-novel-hierarchical-binary-tagging-framework","title":"A Novel Cascade Binary Tagging Framework for Relational Triple Extraction","date":"2019-09-07","arxiv_id":"1909.03227","n_code_links":5,"syntology":null},{"paper":"/paper/rnn-architecture-learning-with-sparse","slug":"rnn-architecture-learning-with-sparse","title":"RNN Architecture Learning with Sparse Regularization","date":"2019-09-06","arxiv_id":"1909.03011","n_code_links":1,"syntology":null},{"paper":"/paper/supervised-multimodal-bitransformers-for","slug":"supervised-multimodal-bitransformers-for","title":"Supervised Multimodal Bitransformers for Classifying Images and Text","date":"2019-09-06","arxiv_id":"1909.02950","n_code_links":6,"syntology":null},{"paper":"/paper/effective-use-of-transformer-networks-for","slug":"effective-use-of-transformer-networks-for","title":"Effective Use of Transformer Networks for Entity Tracking","date":"2019-09-05","arxiv_id":"1909.02635","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":2,"n_instrument":1,"unverified":2,"pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["aditya2211/transformer-entity-tracking"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/in-plain-sight-media-bias-through-the-lens-of","slug":"in-plain-sight-media-bias-through-the-lens-of","title":"In Plain Sight: Media Bias Through the Lens of Factual Reporting","date":"2019-09-05","arxiv_id":"1909.02670","n_code_links":1,"syntology":null},{"paper":"/paper/informing-unsupervised-pretraining-with","slug":"informing-unsupervised-pretraining-with","title":"Specializing Unsupervised Pretraining Models for Word-Level Semantic Similarity","date":"2019-09-05","arxiv_id":"1909.02339","n_code_links":1,"syntology":null},{"paper":"/paper/investigating-berts-knowledge-of-language","slug":"investigating-berts-knowledge-of-language","title":"Investigating BERT's Knowledge of Language: Five Analysis Methods with NPIs","date":"2019-09-05","arxiv_id":"1909.02597","n_code_links":1,"syntology":{"ran":0,"of":3,"n_ran_checked":0,"n_instrument":0,"unverified":3,"pointer_only":3,"phrase":"0 ran · 3 unverified","official":{"repos":["alexwarstadt/data_generation"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"paper":"/paper/semantics-aware-bert-for-language","slug":"semantics-aware-bert-for-language","title":"Semantics-aware BERT for Language Understanding","date":"2019-09-05","arxiv_id":"1909.02209","n_code_links":1,"syntology":{"ran":7,"of":12,"n_ran_checked":5,"n_instrument":2,"unverified":5,"pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","official":{"repos":["cooelf/SemBERT"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"syntax-aware-aspect-level-sentiment","title":"Syntax-Aware Aspect Level Sentiment Classification with Graph Attention Networks","date":"2019-09-05","arxiv_id":"1909.02606","n_code_links":0,"syntology":null},{"paper":"/paper/encode-tag-realize-high-precision-text","slug":"encode-tag-realize-high-precision-text","title":"Encode, Tag, Realize: High-Precision Text Editing","date":"2019-09-03","arxiv_id":"1909.01187","n_code_links":5,"syntology":{"ran":8,"of":11,"n_ran_checked":7,"n_instrument":1,"unverified":3,"pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["google-research/lasertagger"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/language-models-as-knowledge-bases","slug":"language-models-as-knowledge-bases","title":"Language Models as Knowledge Bases?","date":"2019-09-03","arxiv_id":"1909.01066","n_code_links":1,"syntology":null},{"paper":null,"slug":"multimodal-deep-learning-for-mental-disorders","title":"Multimodal Deep Learning for Mental Disorders Prediction from Audio Speech Samples","date":"2019-09-03","arxiv_id":"1909.01067","n_code_links":0,"syntology":null},{"paper":"/paper/transfer-fine-tuning-a-bert-case-study","slug":"transfer-fine-tuning-a-bert-case-study","title":"Transfer Fine-Tuning: A BERT Case Study","date":"2019-09-03","arxiv_id":"1909.00931","n_code_links":1,"syntology":null},{"paper":null,"slug":"unicoder-a-universal-language-encoder-by-pre","title":"Unicoder: A Universal Language Encoder by Pre-training with Multiple Cross-lingual Tasks","date":"2019-09-03","arxiv_id":"1909.00964","n_code_links":0,"syntology":null},{"paper":"/paper/how-contextual-are-contextualized-word","slug":"how-contextual-are-contextualized-word","title":"How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings","date":"2019-09-02","arxiv_id":"1909.00512","n_code_links":1,"syntology":null},{"paper":"/paper/sumqe-a-bert-based-summary-quality-estimation","slug":"sumqe-a-bert-based-summary-quality-estimation","title":"SumQE: a BERT-based Summary Quality Estimation Model","date":"2019-09-02","arxiv_id":"1909.00578","n_code_links":1,"syntology":null},{"paper":null,"slug":"classification-approaches-to-identify","title":"Classification Approaches to Identify Informative Tweets","date":"2019-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/cross-lingual-machine-reading-comprehension","slug":"cross-lingual-machine-reading-comprehension","title":"Cross-Lingual Machine Reading Comprehension","date":"2019-09-01","arxiv_id":"1909.00361","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluating-the-cross-lingual-effectiveness-of","title":"Evaluating the Cross-Lingual Effectiveness of Massively Multilingual Neural Machine Translation","date":"2019-09-01","arxiv_id":"1909.00437","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluation-of-stacked-embeddings-for","title":"Evaluation of Stacked Embeddings for Bulgarian on the Downstream Tasks POS and NERC","date":"2019-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluation-of-vector-embedding-models-in","title":"Evaluation of vector embedding models in clustering of text documents","date":"2019-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"friendsqa-open-domain-question-answering-on","title":"FriendsQA: Open-Domain Question Answering on TV Show Transcripts","date":"2019-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/incidental-supervision-from-question","slug":"incidental-supervision-from-question","title":"QuASE: Question-Answer Driven Sentence Encoding","date":"2019-09-01","arxiv_id":"1909.00333","n_code_links":1,"syntology":null},{"paper":null,"slug":"multilingual-language-models-for-named-entity","title":"Multilingual Language Models for Named Entity Recognition in German and English","date":"2019-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"multilingual-probing-of-deep-pre-trained","title":"Multilingual Probing of Deep Pre-Trained Contextual Encoders","date":"2019-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"predicting-sentiment-of-polish-language-short","title":"Predicting Sentiment of Polish Language Short Texts","date":"2019-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"semantic-role-labeling-with-pretrained","title":"Semantic Role Labeling with Pretrained Language Models for Known and Unknown Predicates","date":"2019-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"adversarial-learning-with-contextual","title":"Adversarial Learning with Contextual Embeddings for Zero-resource Cross-lingual Classification and NER","date":"2019-08-31","arxiv_id":"1909.00153","n_code_links":0,"syntology":null},{"paper":"/paper/evaluation-benchmarks-and-learning","slug":"evaluation-benchmarks-and-learning","title":"Evaluation Benchmarks and Learning Criteria for Discourse-Aware Sentence Representations","date":"2019-08-31","arxiv_id":"1909.00142","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ZeweiChu/DiscoEval"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"knowledge-enhanced-attention-for-robust","title":"Knowledge Enhanced Attention for Robust Natural Language Inference","date":"2019-08-31","arxiv_id":"1909.00102","n_code_links":0,"syntology":null},{"paper":"/paper/nezha-neural-contextualized-representation","slug":"nezha-neural-contextualized-representation","title":"NEZHA: Neural Contextualized Representation for Chinese Language Understanding","date":"2019-08-31","arxiv_id":"1909.00204","n_code_links":10,"syntology":null}],"record_sha256":"a53a39d8e70312a5d7b83c748ac8835a73493c1364e78e0928aac5c04c9782eb","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}